Skip to main content
Figure 6 | EPJ Quantum Technology

Figure 6

From: A coherent perceptron for all-optical learning

Figure 6

Single trajectory divided into a training interval \(\pmb{0 \le t \le M_{\mathrm{train}}\Delta t}\) during which the learning feedback is active and a test interval \(\pmb{M_{\mathrm{train}}\Delta t < t \le M_{\mathrm{test}}\Delta t}\) . During training and testing, respectively, the system is driven by \(M_{\mathrm{train}} = M_{\mathrm{test}} = 100\) separate input states which are held constant for an interval \(\Delta t = 2 \kappa^{-1}\). The estimated class label is discretized by averaging the output intensity over each input interval, dividing the result by the intensity \(|\zeta |^{2}\) corresponding to the logical ‘1’ output state and rounding. The upper panel compares the correct class label y (green) with the estimated class label \(\hat{y}\) (black) during training and testing, respectively. The area between them indicates errors or at least lag of the estimator and is shaded in light red. The second panel shows occurrences of classification errors (red vertical bars). The slight shading near the beginning and the end of the trajectory in the second panel visualizes the segments corresponding to the upper left and right panel, respectively. The third panel shows the learned linear amplitude gains for each synapse. After the learning feedback is turned off at \(t=M_{\mathrm{train}}\Delta t\), they diffuse slightly due to optical shot noise.

Back to article page